基于独立电驱动履带车辆的地面参量估计方法研究
|
摘要
以独立电驱动履带车辆的大量试验数据为依托,提出一种基于驱动力统计学预测模型与车辆动力学模型相结合的算法,对道路阻力系数与转向阻力系数进行估计。根据过零航向角偏差点对车辆的行驶路径进行分割,并利用高斯混合模型对各路径段进行多元聚类,利用连续3个路径段的聚类标签表征运动基元的类型;以基元类型为依据实现数据的分组,利用高斯混合模型构建驱动力统计学预测模型。在进行地面参量估计时,当确定运动基元类型后,通过调用对应的驱动力统计学预测模型,利用高斯混合回归对两侧主动轮转矩进行预测。利用非线性最小二乘法,使得基于驱动力统计学预测模型得到的转矩预测值与基于动力学方程表征的转矩理论值误差最小,从而获得地面参量估计值。对实车采集到的数据进行处理,得到地面参量的测试值并与估计值进行对比,证明了该方法可以在使用较少传感器前提下,保证预测结果的精度与整体算法的效率。
An algorithm combining the driving force statistical prediction model and the vehicle dynamics model is established to estimate the ground parameters based on the experimental data of independent electric tracked vehicles. The path is segmented according to the deviation point of zero course angle,and the Gaussian mixture model( GMM) is used for the multivariate clustering of path segments. The clustering tags of three consecutive path segments are used to represent the types of motion primitive; the data is grouped based on the types of motion primitive,and then GMM is used to build a statistical prediction model. When the ground parameters are estimated,the driving wheel torques are predicted by calling the driving force statistical prediction model and using the Gaussian mixture regression( GMR) after the primitive type is determined. The nonlinear least squares method is used to minimize the errors of the predicted torque values from the statistical prediction model and the theoretical torque values characterized by a kinetic equation,thereby gaining the estimated values of ground parameters. The test values of ground parameters are obtained by processing the data collected from real vehicles compared with the estimated values. The results show that the proposed method can be used to guarantee the precision of predicted results and the overall efficiency of the algorithm on the premise that fewer sensors are used.
An algorithm combining the driving force statistical prediction model and the vehicle dynamics model is established to estimate the ground parameters based on the experimental data of independent electric tracked vehicles. The path is segmented according to the deviation point of zero course angle,and the Gaussian mixture model( GMM) is used for the multivariate clustering of path segments. The clustering tags of three consecutive path segments are used to represent the types of motion primitive; the data is grouped based on the types of motion primitive,and then GMM is used to build a statistical prediction model. When the ground parameters are estimated,the driving wheel torques are predicted by calling the driving force statistical prediction model and using the Gaussian mixture regression( GMR) after the primitive type is determined. The nonlinear least squares method is used to minimize the errors of the predicted torque values from the statistical prediction model and the theoretical torque values characterized by a kinetic equation,thereby gaining the estimated values of ground parameters. The test values of ground parameters are obtained by processing the data collected from real vehicles compared with the estimated values. The results show that the proposed method can be used to guarantee the precision of predicted results and the overall efficiency of the algorithm on the premise that fewer sensors are used.
引文
[1] MARTINEZ J L,MANDOW A,MORALES J,et al. Kinematic modelling of tracked vehicles by experimental identification[C]∥Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. Sendal,Japan:IEEE,2004:1487-1492.
[2]程军伟,高连华,王红岩.基于打滑条件下的履带车辆转向分析[J].机械工程学报,2006,42(增刊):192-195.CHENG J W,GAO L H,WANG H Y. Steering analysis of tracked vehicle under skid condition[J]. Chinese Journal of Mechanical Engineering,2006,42(S):192-195.(in Chinese)
[3] KIM T,KIM W,CHOI S,et al. Path tracking for a skid-steer vehicle using model predictive control with on-line sparse Gaussian process[J]. IFAC-PapersOnLine,2017,50(1):5755-5760.
[4]王博洋,龚建伟,高天云,等.基于高斯混合-隐马尔可夫模型的速差转向履带车辆横向控制驾驶员模型[J].兵工学报,2017,38(12):2301-2308.WANG B Y,GONG J W,GAO T Y,et al. Steering control driver model of skid steering vehicle based on Gaussian mixture modelhidden Markov model[J]. Acta Armamentarii,2017,38(12):2301-2308.(in Chinese)
[5] WANG B Y,LI Z R,GONG J W,et al. Learning and generalizing motion primitives from driving data for path-tracking applications[C]∥Proceedings of 2018 IEEE Intelligent Vehicles Symposium. Changshu,Jiangsu,China:IEEE,2018:1191-1196.
[6] BENDER A,AGAMENNONI G,WARD J R,et al. An unsupervised approach for inferring driver behavior from naturalistic driving data[J]. IEEE Transactions on Intelligent Transportation Systems,2015,16(6):3325-3336.
[7] MANSCHITZ S,KOBER J,GIENGER M,et al. Learning to sequence movement primitives from demonstrations[C]∥Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. Chicago,IL,US:IEEE,2014:4414-4421.
[8] IJSPEERT A J,NAKANISHI J,HOFFMANN H,et al. Dynamical movement primitives:learning attractor models for motor behaviors[J]. Neural Computation,2013,25(2):328-373.
[9]许烁,喻凡,罗哲.气垫车辆土壤参数估值算法[J].上海交通大学学报,2011,45(4):451-456.XU S,YU F,LUO Z. Estimation algorithm of air cushion vehicle soil parameters[J]. Journal of Shanghai Jiaotong University,2011,45(4):451-456.(in Chinese)
[10]许烁,罗哲,纪赜.气垫式越野机器人土壤参数识别算法及其采样点选取规则[J].机械工程学报,2012,48(15):38-46.XU S,LUO Z,JI Z. Soil parameter identification algorithm and sampling point selection rules of air-cushioned off-road robot[J]. Journal of Mechanical Engineering,2012,48(15):38-46.(in Chinese)
[11] BEKKER M G. Introduction to terrain-vehicle systems[M]. Ann Arbor,MI,US:The University of Michigan Press,1969.
[12] HUTANGKALODEE S,ZWEIRI Y H,SENEVIRATNE L D,et al. Multi-solution problem for track-terrain interaction dynamics and lumped soil parameter identification[M]∥CORKE P,SUKKARIAH S. Field and service robotics. Heidelberg,Germany:Springer-Verlag,2006:517-528.
[13]方志强,王红岩,贺小军,等.一种测定履带车辆行驶地面性质参数的新方法[J].兵工学报,2007,28(4):391-395.FANG Z Q,WANG H Y,HE X J,et al. A new method to measure the parameters of ground properties for tracked vehicles[J]. Acta Armamentarii,2007,28(4):391-395,(in Chinese)
[14]郭晓林,杜传沛.基于模型试验的履带车直线行驶阻力研究[J].农业装备与车辆工程,2016,54(8):47-49.GUO X L,DU C P. Research on the linear running resistance of tracked vehicle based on model test[J]. Agricultural Equipment&Vehicle Engineering,2016,54(8):47-49.(in Chinese)
[15]王洪涛.履带车辆差速转向载荷比受软土地面条件影响的实验研究[D].哈尔滨:东北农业大学,2014.WANG H T. Experimental study of differential steering load ratio of tracked vehicles affected by soft soil surface conditions[D].Harbin:Northeast Agricultural University,2014.(in Chinese)
[16] ORDONEZ C,GUPTA N,REESE B,et al. Learning of skidsteered kinematic and dynamic models for motion planning[J].Robotics and Autonomous Systems,2017,95:207-221.
[17]汪明德,赵毓琴,祝嘉光.坦克行驶原理[M].北京:国防工业出版社,1983.WANG M D,ZHAO Y Q,ZHU J G. Theory of tank running[M].Beijing:National Defense Industry Press,1983.(in Chinese)
[2]程军伟,高连华,王红岩.基于打滑条件下的履带车辆转向分析[J].机械工程学报,2006,42(增刊):192-195.CHENG J W,GAO L H,WANG H Y. Steering analysis of tracked vehicle under skid condition[J]. Chinese Journal of Mechanical Engineering,2006,42(S):192-195.(in Chinese)
[3] KIM T,KIM W,CHOI S,et al. Path tracking for a skid-steer vehicle using model predictive control with on-line sparse Gaussian process[J]. IFAC-PapersOnLine,2017,50(1):5755-5760.
[4]王博洋,龚建伟,高天云,等.基于高斯混合-隐马尔可夫模型的速差转向履带车辆横向控制驾驶员模型[J].兵工学报,2017,38(12):2301-2308.WANG B Y,GONG J W,GAO T Y,et al. Steering control driver model of skid steering vehicle based on Gaussian mixture modelhidden Markov model[J]. Acta Armamentarii,2017,38(12):2301-2308.(in Chinese)
[5] WANG B Y,LI Z R,GONG J W,et al. Learning and generalizing motion primitives from driving data for path-tracking applications[C]∥Proceedings of 2018 IEEE Intelligent Vehicles Symposium. Changshu,Jiangsu,China:IEEE,2018:1191-1196.
[6] BENDER A,AGAMENNONI G,WARD J R,et al. An unsupervised approach for inferring driver behavior from naturalistic driving data[J]. IEEE Transactions on Intelligent Transportation Systems,2015,16(6):3325-3336.
[7] MANSCHITZ S,KOBER J,GIENGER M,et al. Learning to sequence movement primitives from demonstrations[C]∥Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. Chicago,IL,US:IEEE,2014:4414-4421.
[8] IJSPEERT A J,NAKANISHI J,HOFFMANN H,et al. Dynamical movement primitives:learning attractor models for motor behaviors[J]. Neural Computation,2013,25(2):328-373.
[9]许烁,喻凡,罗哲.气垫车辆土壤参数估值算法[J].上海交通大学学报,2011,45(4):451-456.XU S,YU F,LUO Z. Estimation algorithm of air cushion vehicle soil parameters[J]. Journal of Shanghai Jiaotong University,2011,45(4):451-456.(in Chinese)
[10]许烁,罗哲,纪赜.气垫式越野机器人土壤参数识别算法及其采样点选取规则[J].机械工程学报,2012,48(15):38-46.XU S,LUO Z,JI Z. Soil parameter identification algorithm and sampling point selection rules of air-cushioned off-road robot[J]. Journal of Mechanical Engineering,2012,48(15):38-46.(in Chinese)
[11] BEKKER M G. Introduction to terrain-vehicle systems[M]. Ann Arbor,MI,US:The University of Michigan Press,1969.
[12] HUTANGKALODEE S,ZWEIRI Y H,SENEVIRATNE L D,et al. Multi-solution problem for track-terrain interaction dynamics and lumped soil parameter identification[M]∥CORKE P,SUKKARIAH S. Field and service robotics. Heidelberg,Germany:Springer-Verlag,2006:517-528.
[13]方志强,王红岩,贺小军,等.一种测定履带车辆行驶地面性质参数的新方法[J].兵工学报,2007,28(4):391-395.FANG Z Q,WANG H Y,HE X J,et al. A new method to measure the parameters of ground properties for tracked vehicles[J]. Acta Armamentarii,2007,28(4):391-395,(in Chinese)
[14]郭晓林,杜传沛.基于模型试验的履带车直线行驶阻力研究[J].农业装备与车辆工程,2016,54(8):47-49.GUO X L,DU C P. Research on the linear running resistance of tracked vehicle based on model test[J]. Agricultural Equipment&Vehicle Engineering,2016,54(8):47-49.(in Chinese)
[15]王洪涛.履带车辆差速转向载荷比受软土地面条件影响的实验研究[D].哈尔滨:东北农业大学,2014.WANG H T. Experimental study of differential steering load ratio of tracked vehicles affected by soft soil surface conditions[D].Harbin:Northeast Agricultural University,2014.(in Chinese)
[16] ORDONEZ C,GUPTA N,REESE B,et al. Learning of skidsteered kinematic and dynamic models for motion planning[J].Robotics and Autonomous Systems,2017,95:207-221.
[17]汪明德,赵毓琴,祝嘉光.坦克行驶原理[M].北京:国防工业出版社,1983.WANG M D,ZHAO Y Q,ZHU J G. Theory of tank running[M].Beijing:National Defense Industry Press,1983.(in Chinese)